.ipynb_checkpoints/config-checkpoint.json

{
  "_name_or_path": "taozi555/hiwaifu-12b-v1.1-fp8",
  "architectures": [
    "MistralForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 5120,
  "initializer_range": 0.02,
  "intermediate_size": 14336,
  "max_position_embeddings": 1024000,
  "model_type": "mistral",
  "num_attention_heads": 32,
  "num_hidden_layers": 40,
  "num_key_value_heads": 8,
  "quantization_config": {
    "activation_scheme": "static",
    "ignored_layers": [
      "model.layers.38.mlp.gate_proj",
      "model.layers.21.mlp.gate_proj",
      "model.layers.28.mlp.gate_proj",
      "model.layers.31.mlp.gate_proj",
      "model.layers.0.mlp.gate_proj",
      "model.layers.30.mlp.gate_proj",
      "model.layers.6.mlp.gate_proj",
      "model.layers.25.mlp.gate_proj",
      "model.layers.33.mlp.gate_proj",
      "model.layers.8.mlp.gate_proj",
      "model.layers.36.mlp.gate_proj",
      "model.layers.24.mlp.gate_proj",
      "model.layers.11.mlp.gate_proj",
      "model.layers.1.mlp.gate_proj",
      "model.layers.13.mlp.gate_proj",
      "model.layers.23.mlp.gate_proj",
      "model.layers.15.mlp.gate_proj",
      "model.layers.17.mlp.gate_proj",
      "model.layers.5.mlp.gate_proj",
      "model.layers.26.mlp.gate_proj",
      "model.layers.29.mlp.gate_proj",
      "model.layers.37.mlp.gate_proj",
      "model.layers.12.mlp.gate_proj",
      "model.layers.4.mlp.gate_proj",
      "model.layers.39.mlp.gate_proj",
      "model.layers.9.mlp.gate_proj",
      "model.layers.19.mlp.gate_proj",
      "lm_head",
      "model.layers.34.mlp.gate_proj",
      "model.layers.3.mlp.gate_proj",
      "model.layers.10.mlp.gate_proj",
      "model.layers.2.mlp.gate_proj",
      "model.layers.20.mlp.gate_proj",
      "model.layers.32.mlp.gate_proj",
      "model.layers.7.mlp.gate_proj",
      "model.layers.16.mlp.gate_proj",
      "model.layers.22.mlp.gate_proj",
      "model.layers.14.mlp.gate_proj",
      "model.layers.35.mlp.gate_proj",
      "model.layers.27.mlp.gate_proj",
      "model.layers.18.mlp.gate_proj"
    ],
    "quant_method": "fp8"
  },
  "rms_norm_eps": 1e-05,
  "rope_theta": 1000000.0,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.46.3",
  "use_cache": true,
  "vocab_size": 131072
}